Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 625 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8038. Min Range: -5.8038
Max Act: 5.8038. Min Act: -0.1700
Data Index: 5446950 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8038. Min Range: -5.8038
Max Act: 5.1788. Min Act: -0.1700
Data Index: 7372124 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8038. Min Range: -5.8038
Max Act: 5.1163. Min Act: -0.1700
Data Index: 5376632 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8038. Min Range: -5.8038
Max Act: 5.1476. Min Act: -0.1700
Data Index: 5529470 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8038. Min Range: -5.8038
Max Act: 5.0538. Min Act: -0.1700
Data Index: 4019787 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8038. Min Range: -5.8038
Max Act: 5.0226. Min Act: -0.1700
Data Index: 4610523 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8038. Min Range: -5.8038
Max Act: 5.0226. Min Act: -0.1700
Data Index: 5613027 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8038. Min Range: -5.8038
Max Act: 4.9913. Min Act: -0.1700
Data Index: 8221791 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8038. Min Range: -5.8038
Max Act: 4.9601. Min Act: -0.1700
Data Index: 4999398 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8038. Min Range: -5.8038
Max Act: 4.8663. Min Act: -0.1700
Data Index: 6714074 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8038. Min Range: -5.8038
Max Act: 4.8976. Min Act: -0.1700
Data Index: 8724156 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8038. Min Range: -5.8038
Max Act: 4.8351. Min Act: -0.1700
Data Index: 7502214 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8038. Min Range: -5.8038
Max Act: 4.8351. Min Act: -0.1700
Data Index: 6092758 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8038. Min Range: -5.8038
Max Act: 4.8351. Min Act: -0.1700
Data Index: 7119981 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8038. Min Range: -5.8038
Max Act: 4.8038. Min Act: -0.1700
Data Index: 7758096 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8038. Min Range: -5.8038
Max Act: 4.8038. Min Act: -0.1700
Data Index: 7197126 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8038. Min Range: -5.8038
Max Act: 4.8038. Min Act: -0.1700
Data Index: 7119979 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8038. Min Range: -5.8038
Max Act: 4.7726. Min Act: -0.1700
Data Index: 389091 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8038. Min Range: -5.8038
Max Act: 4.8038. Min Act: -0.1700
Data Index: 5708261 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8038. Min Range: -5.8038
Max Act: 4.7726. Min Act: -0.1700
Data Index: 254844 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #19